Unverified50% confidenceFactExact time
There are two ways to enable the Ultrafast service tier: set providerOptions.openai.serviceTier to 'ultrafast' in the AI SDK, or set service_tier to 'ultrafast' in Chat Completions and Responses requests.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/17/2026
First Seen
Valid until: 2/15/2027
Sources
Related Entities
Related Claims
UnverifiedAzure OpenAI's parameter support pace is not synchronized with the OpenAI main site, and some older deployments (such as gpt-35-turbo) still only accept max_tokens; the compatibility layer must route by model family, otherwise requests may be rejected by the gateway with a 400.73% similarUnverifiedOpenAI has not disclosed the specific technical approach behind Ultrafast.70% similarUnverifiedOpenAI introduced the Ultra Fast service tier: up to 8x faster in Codex with 300 tokens per second generated, and up to 6x faster in the API.69% similarVerifiedThe core of the OpenAI-compatible protocol is the /v1/chat/completions REST interface specification, which defines fields such as model, messages, and temperature, as well as the streaming response (Server-Sent Events) format.68% similarUnverifiedVendors such as OpenAI and Anthropic have both launched speed-priority models optimized for high-frequency API calls.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1181410API
curl https://kongchang.com/api/v1/knowledge/claims/1181410MCP
get_claim(id=1181410)